Quantized Kernel Recursive Least Squares Algorithm

In a recent paper, we developed a novel quantized kernel least mean square algorithm, in which the input space is quantized (partitioned into smaller regions) and the network size is upper bounded by the quantization codebook size (number of the regions). In this paper, we propose the quantized kern...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems Vol. 24; no. 9; pp. 1484 - 1491
Main Authors: Chen, Badong, Zhao, Songlin, Zhu, Pingping, Principe, Jose C.
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.09.2013
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Applied sciences
Bioinformatics
Coding, codes
Computer science; control theory; systems
Computer simulation
Controllability
Data processing. List processing. Character string processing
Exact sciences and technology
Information, signal and communications theory
Kernel
Kernel recursive least squares (KRLS)
Kernels
Learning systems
Least squares method
Manganese
Memory organisation. Data processing
On-line systems
Partitioning algorithms
quantization
Quantization (signal)
quantized kernel recursive least squares (QKRLS)
Recursive
Regression
Signal and communications theory
Software
sparsification
Telecommunications and information theory
Vector quantization
Cluster analysis
Monte Carlo method
Vector quantization
Updating
Regression analysis
Vector method
Recursive algorithm
Modeling
Kernel method
Upper bound
Codebook
Kernel recursive least squares (KRLS)
Least squares method
Signal quantization
Optimal solution
sparsification
Sparse representation
quantized kernel recursive least squares (QKRLS)
quantization
ISSN:2162-237X, 2162-2388, 2162-2388
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In a recent paper, we developed a novel quantized kernel least mean square algorithm, in which the input space is quantized (partitioned into smaller regions) and the network size is upper bounded by the quantization codebook size (number of the regions). In this paper, we propose the quantized kernel least squares regression, and derive the optimal solution. By incorporating a simple online vector quantization method, we derive a recursive algorithm to update the solution, namely the quantized kernel recursive least squares algorithm. The good performance of the new algorithm is demonstrated by Monte Carlo simulations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2013.2258936